FedSEAL: Semi-Supervised Federated Learning with Self-Ensemble Learning and Negative Learning
This addresses a practical challenge in federated learning for scenarios where labeling data is difficult, though it appears incremental as it builds on existing SSFL methods.
The paper tackled the problem of semi-supervised federated learning, where clients have unlabeled data and the server has a small labeled dataset, by proposing FedSEAL, which improved accuracy and efficiency using self-ensemble and negative learning, outperforming state-of-the-art methods on Fashion-MNIST and CIFAR10 datasets.
Federated learning (FL), a popular decentralized and privacy-preserving machine learning (FL) framework, has received extensive research attention in recent years. The majority of existing works focus on supervised learning (SL) problems where it is assumed that clients carry labeled datasets while the server has no data. However, in realistic scenarios, clients are often unable to label their data due to the lack of expertise and motivation while the server may host a small amount of labeled data. How to reasonably utilize the server labeled data and the clients' unlabeled data is thus of paramount practical importance. In this paper, we propose a new FL algorithm, called FedSEAL, to solve this Semi-Supervised Federated Learning (SSFL) problem. Our algorithm utilizes self-ensemble learning and complementary negative learning to enhance both the accuracy and the efficiency of clients' unsupervised learning on unlabeled data, and orchestrates the model training on both the server side and the clients' side. Our experimental results on Fashion-MNIST and CIFAR10 datasets in the SSFL setting validate the effectiveness of our method, which outperforms the state-of-the-art SSFL methods by a large margin.